Merge pull request #3798 from StevenPuttemans:add_breakrule_cascade_accuracy

apps/traincascade/cascadeclassifier.cpp

@@ -135,7 +135,8 @@ bool CvCascadeClassifier::train( const string _cascadeDirName,
                                 const CvCascadeParams& _cascadeParams,
                                 const CvFeatureParams& _featureParams,
                                 const CvCascadeBoostParams& _stageParams,
-                                bool baseFormatSave )
+                                bool baseFormatSave,
+                                double acceptanceRatioBreakValue )
 {
     // Start recording clock ticks for training time output
     const clock_t begin_time = clock();
@@ -185,6 +186,7 @@ bool CvCascadeClassifier::train( const string _cascadeDirName,
     cout << "numStages: " << numStages << endl;
     cout << "precalcValBufSize[Mb] : " << _precalcValBufSize << endl;
     cout << "precalcIdxBufSize[Mb] : " << _precalcIdxBufSize << endl;
+    cout << "acceptanceRatioBreakValue : " << acceptanceRatioBreakValue << endl;
     cascadeParams.printAttrs();
     stageParams->printAttrs();
     featureParams->printAttrs();
@@ -216,6 +218,11 @@ bool CvCascadeClassifier::train( const string _cascadeDirName,
                     "Branch training terminated." << endl;
             break;
         }
+        if( (tempLeafFARate <= acceptanceRatioBreakValue) && (acceptanceRatioBreakValue < 0) ){
+            cout << "The required acceptanceRatio for the model has been reached to avoid overfitting of trainingdata. "
+                    "Branch training terminated." << endl;
+            break;
+        }
 
         Ptr<CvCascadeBoost> tempStage = makePtr<CvCascadeBoost>();
         bool isStageTrained = tempStage->train( featureEvaluator,

apps/traincascade/cascadeclassifier.h

@@ -94,7 +94,8 @@ public:
                 const CvCascadeParams& _cascadeParams,
                 const CvFeatureParams& _featureParams,
                 const CvCascadeBoostParams& _stageParams,
-                bool baseFormatSave = false );
+                bool baseFormatSave = false,
+                double acceptanceRatioBreakValue = -1.0 );
 private:
     int predict( int sampleIdx );
     void save( const std::string cascadeDirName, bool baseFormat = false );

apps/traincascade/traincascade.cpp

@@ -15,6 +15,7 @@ int main( int argc, char* argv[] )
     int precalcValBufSize = 1024,
         precalcIdxBufSize = 1024;
     bool baseFormatSave = false;
+    double acceptanceRatioBreakValue = -1.0;
 
     CvCascadeParams cascadeParams;
     CvCascadeBoostParams stageParams;
@@ -36,6 +37,7 @@ int main( int argc, char* argv[] )
         cout << "  [-precalcIdxBufSize <precalculated_idxs_buffer_size_in_Mb = " << precalcIdxBufSize << ">]" << endl;
         cout << "  [-baseFormatSave]" << endl;
         cout << "  [-numThreads <max_number_of_threads = " << numThreads << ">]" << endl;
+        cout << "  [-acceptanceRatioBreakValue <value> = " << acceptanceRatioBreakValue << ">]" << endl;
         cascadeParams.printDefaults();
         stageParams.printDefaults();
         for( int fi = 0; fi < fc; fi++ )
@@ -86,6 +88,10 @@ int main( int argc, char* argv[] )
         {
           numThreads = atoi(argv[++i]);
         }
+        else if( !strcmp( argv[i], "-acceptanceRatioBreakValue" ) )
+        {
+          acceptanceRatioBreakValue = atof(argv[++i]);
+        }
         else if ( cascadeParams.scanAttr( argv[i], argv[i+1] ) ) { i++; }
         else if ( stageParams.scanAttr( argv[i], argv[i+1] ) ) { i++; }
         else if ( !set )
@@ -112,6 +118,7 @@ int main( int argc, char* argv[] )
                       cascadeParams,
                       *featureParams[cascadeParams.featureType],
                       stageParams,
-                      baseFormatSave );
+                      baseFormatSave,
+                      acceptanceRatioBreakValue );
     return 0;
 }

doc/user_guide/ug_traincascade.markdown

@@ -256,6 +256,12 @@ Command line arguments of opencv_traincascade application grouped by purposes:
         Maximum number of threads to use during training. Notice that the actual number of used
         threads may be lower, depending on your machine and compilation options.
 
+    -   -acceptanceRatioBreakValue \<break_value\>
+
+        This argument is used to determine how precise your model should keep learning and when to stop.
+        A good guideline is to train not further than 10e-5, to ensure the model does not overtrain on your training data.
+        By default this value is set to -1 to disable this feature.
+
 -#  Cascade parameters:
 
     -   -stageType \<BOOST(default)\>